© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 18947
    Prev
    Next
    INDEX
    Explanations

    inorder traversal, sequence sorting, dfs traversal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stat
    -0.07
    å¤ļ大
    -0.07
    agi
    -0.07
    estim
    -0.06
    å®ķ
    -0.06
    ä¸ĵæ¡Ī
    -0.06
    åIJ¸æ°´
    -0.06
    åĮ¹
    -0.06
    .SetFloat
    -0.06
     бли
    -0.06
    POSITIVE LOGITS
    顺åºı
    0.10
     inorder
    0.09
    éłĨåºı
    0.09
    Ñħодом
    0.08
    åħĭåħ°
    0.08
    è¾ĵåĩºçļĦ
    0.08
    IBIL
    0.08
    è¾ĵåĩº
    0.08
     sequence
    0.08
    次åºı
    0.08
    Activations Density 0.005%

    No Known Activations